Like a Baby: Visually Situated Neural Language Acquisition

Alexander Ororbia, Ankur Mali, Matthew Kelly, David Reitter


Abstract
We examine the benefits of visual context in training neural language models to perform next-word prediction. A multi-modal neural architecture is introduced that outperform its equivalent trained on language alone with a 2% decrease in perplexity, even when no visual context is available at test. Fine-tuning the embeddings of a pre-trained state-of-the-art bidirectional language model (BERT) in the language modeling framework yields a 3.5% improvement. The advantage for training with visual context when testing without is robust across different languages (English, German and Spanish) and different models (GRU, LSTM, Delta-RNN, as well as those that use BERT embeddings). Thus, language models perform better when they learn like a baby, i.e, in a multi-modal environment. This finding is compatible with the theory of situated cognition: language is inseparable from its physical context.
Anthology ID:
P19-1506
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Editors:
Anna Korhonen, David Traum, Lluís Màrquez
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5127–5136
Language:
URL:
https://aclanthology.org/P19-1506
DOI:
10.18653/v1/P19-1506
Bibkey:
Cite (ACL):
Alexander Ororbia, Ankur Mali, Matthew Kelly, and David Reitter. 2019. Like a Baby: Visually Situated Neural Language Acquisition. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5127–5136, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Like a Baby: Visually Situated Neural Language Acquisition (Ororbia et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1506.pdf
Supplementary:
 P19-1506.Supplementary.pdf
Video:
 https://aclanthology.org/P19-1506.mp4